CN109597858B - Merchant classification method and device and merchant recommendation method and device - Google Patents
Merchant classification method and device and merchant recommendation method and device Download PDFInfo
- Publication number
- CN109597858B CN109597858B CN201811534645.8A CN201811534645A CN109597858B CN 109597858 B CN109597858 B CN 109597858B CN 201811534645 A CN201811534645 A CN 201811534645A CN 109597858 B CN109597858 B CN 109597858B
- Authority
- CN
- China
- Prior art keywords
- merchant
- classification
- order data
- determining
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Abstract
The embodiment of the invention relates to the technical field of data processing, and discloses a merchant classification method and device and a merchant recommendation method and device. The invention discloses a merchant classification method, which comprises the following steps: acquiring historical order data, and clustering the order data according to user information of the order data; determining classification characteristics according to the relevancy of each merchant in the clustered order data; and classifying the merchants to be classified according to the classification characteristics. The invention also provides a merchant classification device, a merchant recommendation method, a merchant recommendation device, electronic equipment and a nonvolatile storage medium, which can provide a more intelligent classification and recommendation mode and enable a user to obtain a desired merchant more easily.
Description
Technical Field
The invention relates to the field of data processing, in particular to a merchant classification method and device and a merchant recommendation method and device.
Background
The Internet enterprises are developed and grown on the basis of platforms, and the platform mode becomes a symbolic mode in the Internet era. The cloud set of merchants in the platform gathers more merchants and commodities, but makes users dazzling and more difficult to search for desired merchants and commodities.
In the existing platform, a classification mode is generally adopted to provide a selection interface for a user, but simple classification cannot meet various requirements of the user. In the existing classification method, although hierarchical clustering (such as a clustering algorithm of K-means) is adopted, features are extracted from characteristics of merchants, and a specific clustering model is input according to the extracted features and the types to be clustered, so that hierarchical clustering is performed. Clustering into several types has no definite target, so that the clustering effect is not ideal, and meanwhile, the information quantity is not rich enough because only one dimension is used for expressing the characteristics of the commercial tenant.
Disclosure of Invention
The embodiment of the invention aims to provide a merchant classification method and a merchant classification device and a merchant recommendation method and a merchant recommendation device, which can provide a more intelligent classification and recommendation mode and enable a user to obtain a desired merchant more easily.
In order to solve the above technical problem, an embodiment of the present invention provides a merchant classification method, including: acquiring historical order data, and clustering the order data according to user information of the order data; determining classification characteristics according to the relevancy of each merchant in the clustered order data; and classifying the merchants to be classified according to the classification characteristics.
The embodiment of the invention also provides a merchant recommendation method, which comprises the following steps: acquiring historical order data of a user; determining merchant classification to be recommended according to the historical order data and the merchant classification information; recommending subordinate merchants of the determined merchant classification to the user; the merchant classification information is from the merchant classification method.
The embodiment of the present invention further provides a merchant classification device, including: the acquisition module is used for acquiring historical order data; the clustering module is used for clustering the order data according to the user information of the order data; the determining module is used for determining classification characteristics according to the relevancy of each merchant in the clustered order data; and the classification module is used for classifying the merchants to be classified according to the classification characteristics.
The embodiment of the present invention further provides a merchant recommendation apparatus, including: the acquisition module is used for acquiring historical order data of a user; the classification determining module is used for determining the classification of the commercial tenant to be recommended according to the historical order data and the commercial tenant classification information; the recommending module is used for recommending the subordinate merchants of the determined merchant classification to the user; the merchant classification information is from the merchant classification device.
Embodiments of the present invention further provide an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor executes the program to perform: acquiring historical order data, and clustering the order data according to user information of the order data; determining classification characteristics according to the relevancy of each merchant in the clustered order data; and classifying the merchants to be classified according to the classification characteristics.
Embodiments of the present invention further provide an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor executes the program to perform: acquiring historical order data of a user; determining merchant classification to be recommended according to the historical order data and the merchant classification information; recommending subordinate merchants of the determined merchant classification to the user; the merchant classification information is from the merchant classification method.
Embodiments of the present invention also provide a non-volatile storage medium for storing a computer-readable program for causing a computer to execute the merchant classification method as described above.
Embodiments of the present invention also provide a non-volatile storage medium for storing a computer-readable program for causing a computer to execute the merchant recommendation method as described above.
Compared with the prior art, the implementation mode of the invention has the main differences and the effects that: starting from order placing data of a user, determining the correlation of merchants, and considering preference consistency implied by order placing of the user, compared with the existing classification mode from the restaurant perspective, the merchant classification method from the order placing perspective of the user is more accurate, and has more referential property for data analysis. And then, determining the merchant classification recommended for the user according to the historical ordering condition of the user and the merchant classification, and then recommending merchants for the user according to the classification. As the merchant classification adopts classification based on the ordering data of the user and covers the preference consistency of the user, the subsequent recommendation is more targeted and better meets the requirements of the user.
As a further improvement, the determining the classification characteristics according to the relevancy of each merchant in the clustered order data specifically includes: determining a training sample according to the relevancy of each merchant in the clustered order data; training by using the training sample to obtain a neural network model, wherein the input of the neural network model is at least two commercial tenants, and the output of the neural network model is the similarity of the at least two commercial tenants; and determining the classification characteristic according to the middle layer of the neural network model. And the classification characteristics influencing the merchant classification result are screened out by using the model, and the characteristic determination is accurate and effective.
As a further improvement, the neural network model is a single-layer neural network model. And a single-layer neural network model is utilized, so that the characteristic determination is simple and quick.
As a further improvement, the intermediate layer is preset with a width, and the larger the width is, the larger the number of the determined features of the classification features is. The feature quantity can be conveniently adjusted by adjusting the width, and the adjustment of the obtained feature quantity by technicians according to needs is facilitated.
As a further improvement, the intermediate layer of the single-layer neural network is obtained by: and minimizing the distance of the merchant with the highest correlation degree, and maximizing the distance of the merchant with the lowest correlation degree to obtain the middle layer. The method of obtaining the intermediate layer is specified.
As a further improvement, the merchant with the highest correlation degree is the merchant ordered by the same user, and the merchant with the lowest correlation degree is the merchant ordered by different users. And (5) determining the relevance.
As a further improvement, the clustering the order data according to the user information of the order data includes: respectively summarizing the order data of the same type of user; the aggregated order data is sorted. A clustering method is defined.
As a further improvement, the classifying the summarized order data specifically includes: and recording the order data belonging to the same class in the classification result as a document file. And establishing a document file to facilitate subsequent data analysis and calling.
Drawings
Fig. 1 is a flowchart of a merchant classification method according to a first embodiment of the present invention;
FIG. 2 is a flow chart of determining classification characteristics in a merchant classification method according to a second embodiment of the present invention;
fig. 3 is a schematic diagram of clustering in the classification method of the merchant according to the second embodiment of the present invention;
FIG. 4 is a schematic diagram of model training in a merchant classification method according to a second embodiment of the present invention;
fig. 5 is a flowchart of a merchant recommendation method according to a third embodiment of the present invention;
FIG. 6 is a schematic diagram of a merchant classifying device according to a fourth embodiment of the present invention;
FIG. 7 is a schematic diagram of a merchant recommendation device in a fifth embodiment according to the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.
Fig. 9 is a schematic structural diagram of an electronic device according to a seventh embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not constitute any limitation to the specific implementation manner of the present invention, and the embodiments may be mutually incorporated and referred to without contradiction.
The first embodiment of the present invention relates to a method for classifying merchants, which may be restaurants, clothing stores, beauty shops, or the like, and is mainly described in detail with restaurants as a main point in the present embodiment. The flow chart is shown in fig. 1, and the method comprises the following steps:
In particular, the historical order data may be from one user, a class of users, or all of the historical order data for a period of time in the platform. More specifically, the order data may include information such as user information, merchant information, order placement time, and order placement amount.
And step 102, clustering order data.
Specifically, the order data is clustered according to the user information of the order data in the step, wherein whether two merchants are similar or not is confirmed during clustering, and the order placing can be determined according to whether the same user places an order or not, and also can be determined according to whether the same type of user places an order or not. That is, in this step, order data issued by the same type of user (or the same user) may be summarized respectively; the aggregated order data is sorted.
Furthermore, since one user may place an order in different merchants, and the personal preference of the same user is basically unchanged, the merchants placing the order by the same user hide the possibility of placing the order by users with similar preferences, determine whether two merchants are similar according to whether the same user places the order, and consider the implicit consistency of the user placing the order, so that the classification result is closer to the user's requirement.
Such as: if the historical orders of a certain user respectively comprise orders in kendyr and in mcdonald, the similar orders of the kendyr and the mcdonald can be determined according to the fact that the same user places orders. It can be found that in practical application, users can select merchants with similar taste and style to place orders, so that the merchants are classified into one category, which is beneficial to determining the potential merchants for placing orders.
It should be noted that, in this step, the order data belonging to the same category in the classification result is recorded as a document file. The historical orders of a single user can accurately depict the taste, address and other information of the single user, a series of historical orders of the single user are taken as a document file, and the files are used for calling and analyzing data more simply and directly.
The steps 101 and 102 are a data preparation stage, and in this stage, operations such as cleaning and denoising can be performed on the prepared data as needed, which are not described herein again.
And 103, determining classification characteristics according to the correlation of each merchant in the clustered order data.
Specifically, the classification features can be obtained by analyzing the merchants with similar orders placed by the users determined according to historical order data, and common features of the merchants with similar orders placed by the users are extracted to serve as the classification features.
More specifically, the correlation may have a preset determination rule, the merchant with the highest correlation is the merchant ordered by the same user, and the merchant with the lowest correlation is the merchant ordered by different users. The correlation can be quantified as numbers, such as 1 and 0, where 1 represents the highest correlation, and 0 represents the lowest correlation, and the numbers can be expressed as percentage numbers instead of integers, which are not listed here.
And 104, classifying the merchants to be classified according to the classification characteristics.
Specifically, the classification features are bases for classifying the merchants to be classified, and classification features determined in step 103 can be used for classification.
It can be seen that, compared with the prior art, the main differences and effects of the present embodiment are as follows: starting from order placing data of a user, determining the correlation of merchants, and considering preference consistency implied by order placing of the user, compared with the existing classification mode from the restaurant perspective, the merchant classification method is more accurate in order placing of the user, more referential is provided for data analysis, and more accurate is provided when commodity recommendation is needed.
In addition, the method can be applied to clothing stores, and because the same user has the characteristic of preference consistency when wearing clothing, different clothing stores which are ordered by the same user have the characteristic of similarity of the ordered users and are classified according to the ordered users, so that the clothing stores which belong to one category are ordered by the same user, or the ordering probability of the same user is higher, and the subsequent accurate clothing recommendation is facilitated.
A second embodiment of the present invention relates to a merchant classification method.
The embodiment defines a specific way of determining the classification features according to the correlation, determines the classification features in a model training way, and the determination process of the classification features is shown in fig. 2, and specifically comprises the following steps:
Specifically, for example, the order data clustering is performed by the same user, the order data placed by the same user are clustered into one type, that is, the order data are clustered for each user. In practical application, order data clustering can be performed on users of a same class (user classification can be reserved), and order data placed by users of the same class are clustered into a same class.
In the embodiment, two merchants may be used as one training sample, the correlation between merchants with the same order made by the same user is determined as 1, the correlation between merchants without the same order made by the same user is determined as 0, then, in merchants with the correlation of 1, two merchants may be combined into one training sample, and in merchants with the same correlation of 0, two merchants may be combined into one training sample. In this embodiment, the number of the merchants in each training sample group is 2, and in practical application, the number of the merchants in each training sample group can be selected according to practice, and is not listed here.
And 202, training by using the training sample to obtain a neural network model.
Specifically, the training is performed by using the training samples determined in step 201, the input of the neural network model used for training is at least two merchants (a set of training samples), and the output is the similarity of at least two merchants (the correlation of the set of training samples).
More specifically, the neural network model in this embodiment may be a single-layer neural network model, which simplifies the computational complexity as much as possible.
And step 203, determining classification characteristics according to the middle layer of the neural network.
Specifically, after the training is completed, the hidden intermediate layer in the neural network model includes the classification features to be obtained.
It should be noted that the width of the intermediate layer is related to the number of the features of the classification features, and the larger the width is, the larger the number of the determined features of the classification features is. In practical application, the more the number of the obtained classification features is, the higher the subsequent operation complexity is, but the more accurate the obtained classification result is, and the less the number of the classification features is, the lower the subsequent operation complexity is. The width of the intermediate layer can be varied according to the number of features subsequently required.
The above steps 201 to 203 describe how to determine the classification features according to the clustering result according to the model training mode.
The embodiment takes a restaurant as an example, and further explains the classification method of the merchants:
when historical order data are obtained, obtaining the historical order data by taking an example cloud platform as a source; then, order clustering is carried out by ordering of a single user, the clustering result is shown in fig. 3, each user corresponds to one document file, and a series of document files are obtained; next, model training is performed using the order data in each document file, and the training principle is shown in FIG. 4.
In the actual operation process of the model training, a matrix operation mode can be applied, for example, each restaurant is set with an encoded id, the encoding mode is that id corresponding to restaurant a is [0000000 … 01000 … 00000], id corresponding to restaurant B is [0000000 … 00001 … 00000], only one bit in each id is "1", the rest is "0", and the positions of "1" are different.
During training, a series of restaurant ids of the same user who has made an order are input, the pairwise similarity of the restaurants is 1, the restaurant relevance of the non-same user who has made an order is 0, and the steepest descent method and the back propagation method can be adopted, so that the middle layer of the single-layer neural network can be trained.
Further, a single-layer neural network is obtained after training, the distance of the merchant with the highest correlation degree is minimized, the distance of the merchant with the lowest correlation degree is maximized, a hidden middle layer is obtained, and the restaurant clustering feature (namely restaurant vectorization data) is obtained by using the product of the middle layer and the restaurant id.
Therefore, the embodiment definitely utilizes the model to screen out the classification features influencing the merchant classification result, a single-layer neural network is specifically adopted during training, the operation is simplified as much as possible, and the classification features are determined accurately and effectively.
A third embodiment of the present invention relates to a recommendation method for a merchant, where the merchant may also be a restaurant, an apparel store, a beauty shop, or the like, and the present embodiment is mainly described in detail with a restaurant as a main point. The flow chart is shown in fig. 5, and the method comprises the following steps:
Specifically, historical order data of a user to be recommended are obtained.
Specifically, the merchant classification information in this step may adopt the classification information in the merchant classification method in any one of the first embodiment and the second embodiment.
More specifically, the step may specifically include: classifying orders in the historical order data according to the merchant classification information; and determining the merchant classification to be recommended according to the classification result. In this embodiment, the historical orders are classified according to the category of the merchant to which the order belongs, the orders of the merchants in the same category are classified into one category, and then the historical order number in each category is determined, so that the category with the largest historical order number can be determined as the category of the merchant to be recommended.
In practical applications, besides the above confirmation method, the merchant classification to be recommended may also be confirmed in the following manner: respectively determining commercial tenants to which orders in the historical order data belong; classifying the determined commercial tenants according to the commercial tenant classification information; and determining the merchant classification to be recommended according to the classification result. Specifically, the merchants to which the historical orders belong are determined, then the classifications of the merchants are determined, the merchants of the same classification are classified into one class, then the number of the merchants in each classification is determined, and the classification with the largest number of the merchants can be determined as the merchant classification to be recommended.
Specifically, after the merchant to be recommended is classified and confirmed, the merchant under the classification may be recommended to the user, wherein during the recommendation, all merchants under the classification may be specifically recommended, or a part of merchants under the classification may be recommended, and the number of recommended merchants may be set according to actual needs, which is not limited herein.
It can be seen that, in the present embodiment, the merchant recommendation is performed on the user by using the classification method in the first embodiment or the second embodiment, which is a practical application of the classification method. The classification basis is obtained from the purchasing behavior of the user, so the determined classification is more in line with the purchasing habit of the user, the recommendation method in the embodiment is more in line with the user requirements, and the recommendation result is more accurate and targeted.
Moreover, since all technical solutions in the first embodiment or the second embodiment are applied to this embodiment, the technical details described in the first embodiment or the second embodiment are also applicable to this embodiment, and are not described herein again.
A fourth embodiment of the present invention relates to a sorting apparatus for a merchant, as shown in fig. 6, the apparatus including:
and the acquisition module is used for acquiring historical order data.
And the clustering module is used for clustering the order data according to the user information of the order data.
And the determining module is used for determining the classification characteristics according to the relevancy of each merchant in the clustered order data.
And the classification module is used for classifying the merchants to be classified according to the classification characteristics.
In one example, the clustering module specifically includes:
and the sample determining submodule is used for determining a training sample according to the correlation of each merchant in the clustered order data.
And the training submodule is used for training by utilizing the training sample to obtain the neural network model. Specifically, the input of the neural network model is at least two merchants, and the output is the similarity of the at least two merchants.
And the determining submodule is used for determining the classification characteristics according to the middle layer of the neural network model.
In one example, the neural network model may be a single layer neural network model.
In one example, the intermediate layer may be preset with a width, wherein the larger the width is, the larger the number of features of the determined classification features is.
In one example, the intermediate layer of the single-layer neural network described above is obtained using: and minimizing the distance of the merchant with the highest correlation degree, and maximizing the distance of the merchant with the lowest correlation degree to obtain the middle layer.
In one example, the merchant with the highest correlation is the merchant ordered by the same user, and the merchant with the lowest correlation is the merchant ordered by different users.
In one example, the clustering module may specifically include:
and the summarizing submodule is used for summarizing the order data issued by the same type of users.
And the classification submodule is used for classifying the summarized order data.
In one example, the classification sub-module records the order data belonging to the same class in the classification result as a document file.
It can be seen that, compared with the prior art, the main differences and effects of the present embodiment are as follows: starting from order placing data of a user, determining the correlation of merchants, and considering preference consistency implied by order placing of the user, compared with the existing classification mode from the restaurant perspective, the merchant classification method is more accurate in order placing of the user, more referential is provided for data analysis, and more accurate is provided when commodity recommendation is needed.
It should be understood that this embodiment is an example of the apparatus corresponding to the first embodiment, and may be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that each module referred to in this embodiment is a logical module, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that other elements are not present in the present embodiment.
A fifth embodiment of the present invention relates to a business recommendation apparatus, as shown in fig. 7, including:
and the acquisition module is used for acquiring historical order data of the user.
And the classification determining module is used for determining the classification of the commercial tenant to be recommended according to the historical order data and the commercial tenant classification information.
And the recommending module is used for recommending the determined subordinate merchants of the merchant classification to the user.
The merchant classification information is from the classification device of the merchant in the fourth embodiment.
In one example, the classification determination module may specifically include:
and the first classification submodule is used for classifying the orders in the historical order data according to the merchant classification information.
And the first determining submodule is used for determining the merchant classification to be recommended according to the classification result.
In another example, the classification determination module may specifically include:
and the second determining submodule is used for respectively determining the merchants to which the orders in the historical order data belong.
And the second classification submodule is used for classifying the determined commercial tenants according to the commercial tenant classification information.
And the third determining submodule is used for determining the merchant classification to be recommended according to the classification result.
It can be seen that, compared with the prior art, the main differences and effects of the present embodiment are as follows: the present embodiment is a practical application of the classification device in the fourth embodiment to a user for recommending merchants. The classification basis is obtained from the purchasing behavior of the user, so the determined classification is more in line with the purchasing habit of the user, the recommendation method in the embodiment is more in line with the user requirements, and the recommendation result is more accurate and targeted.
It should be understood that this embodiment is an example of an apparatus corresponding to the third embodiment, and that this embodiment can be implemented in cooperation with the third embodiment. The related technical details mentioned in the third embodiment are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the third embodiment.
It should be noted that each module referred to in this embodiment is a logical module, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that other elements are not present in the present embodiment.
A sixth embodiment of the present invention relates to an electronic apparatus, as shown in fig. 8, including: at least one processor 801; and a memory 802 communicatively coupled to the at least one processor 801; and a communication component 803 communicatively coupled to the scanning device, the communication component 803 receiving and transmitting data under control of the processor 801; wherein the memory 802 stores instructions executable by the at least one processor 801 to implement:
and acquiring historical order data, and clustering the order data according to the user information of the order data.
And determining classification characteristics according to the relevancy of each merchant in the clustered order data.
And classifying the merchants to be classified according to the classification characteristics.
Specifically, the electronic device includes: one or more processors 801 and a memory 802, one processor 801 being illustrated in fig. 8. The processor 801 and the memory 802 may be connected by a bus or other means, and fig. 8 illustrates an example of a connection by a bus. Memory 802, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 801 executes various functional applications and data processing of the device by running nonvolatile software programs, instructions, and modules stored in the memory 802, that is, implements the merchant classification method described above.
The memory 802 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a list of options, etc. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 802 optionally includes memory 802 located remotely from the processor 801, and such remote memory 802 may be connected to an external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more modules are stored in the memory 802 that, when executed by the one or more processors 801, perform the merchant categorization methods of any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, has corresponding functional modules and beneficial effects of the execution method, and can refer to the method provided by the embodiment of the application without detailed technical details in the embodiment.
A seventh embodiment of the present invention relates to an electronic apparatus, as shown in fig. 9, including: at least one processor 901; and, memory 902 communicatively connected to at least one processor 901; and a communication component 903 communicatively coupled to the scanning device, the communication component 903 receiving and transmitting data under the control of the processor 901; wherein the memory 902 stores instructions executable by the at least one processor 901, the instructions being executable by the at least one processor 901 to implement:
acquiring historical order data of a user;
determining merchant classification to be recommended according to historical order data and merchant classification information;
recommending subordinate merchants of the determined merchant classification to the user;
the merchant classification information is from the method for classifying merchants in any one of the first embodiment and the second embodiment.
Specifically, the electronic device includes: one or more processors 901 and a memory 902, where one processor 901 is taken as an example in fig. 9. The processor 901 and the memory 902 may be connected by a bus or by other means, and fig. 9 illustrates the connection by the bus as an example. Memory 902, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 901 executes various functional applications and data processing of the device by running nonvolatile software programs, instructions, and modules stored in the memory 902, that is, implements the merchant recommendation method described above.
The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store a list of options, etc. Further, the memory 902 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 902 may optionally include memory 902 located remotely from the processor 901, and such remote memory 902 may be coupled to the external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more modules are stored in the memory 902 and when executed by the one or more processors 901 perform the merchant recommendation method of any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, has corresponding functional modules and beneficial effects of the execution method, and can refer to the method provided by the embodiment of the application without detailed technical details in the embodiment.
An eighth embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, where the computer-readable program is used for causing a computer to execute some or all of the embodiments of the merchant classification method described above.
A ninth embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, where the computer-readable program is used for causing a computer to execute some or all of the above embodiments of the merchant recommendation method.
That is, as can be understood by those skilled in the art, all or part of the steps in the method according to the above embodiments may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
The embodiment of the application provides A1. a merchant classification method, which comprises the following steps:
acquiring historical order data, and clustering the order data according to user information of the order data;
determining classification characteristics according to the relevancy of each merchant in the clustered order data;
and classifying the merchants to be classified according to the classification characteristics.
A2. According to the merchant classification method described in a1, the determining the classification features according to the relevancy of each merchant in the clustered order data specifically includes:
determining a training sample according to the relevancy of each merchant in the clustered order data;
training by using the training sample to obtain a neural network model, wherein the input of the neural network model is at least two commercial tenants, and the output of the neural network model is the similarity of the at least two commercial tenants;
and determining the classification characteristic according to the middle layer of the neural network model.
A3. According to the merchant classification method described in a2, the neural network model is a single-layer neural network model.
A4. According to the merchant classification method described in a2, the intermediate layer is preset with a width, and the larger the width is, the larger the number of the determined features of the classification features is.
A5. According to the merchant classification method described in a2, the middle layer of the single-layer neural network is obtained by the following method:
and minimizing the distance of the merchant with the highest correlation degree, and maximizing the distance of the merchant with the lowest correlation degree to obtain the middle layer.
A6. According to the merchant classification method described in a1, the merchant with the highest correlation degree is the merchant ordered by the same user, and the merchant with the lowest correlation degree is the merchant ordered by different users.
A7. According to the merchant classification method described in a1, the clustering the order data according to the user information of the order data includes:
respectively summarizing the order data of the same type of user;
the aggregated order data is sorted.
A8. According to the merchant classification method described in a7, the classifying the aggregated order data specifically includes:
and recording the order data belonging to the same class in the classification result as a document file.
The embodiment of the present application further provides B9. a merchant recommendation method, including:
acquiring historical order data of a user;
determining merchant classification to be recommended according to the historical order data and the merchant classification information;
recommending subordinate merchants of the determined merchant classification to the user;
wherein the merchant classification information is from the merchant classification method of any one of the A1-A8.
B10. According to the merchant recommendation method in B9, determining the merchant category to be recommended according to the historical order data and the merchant category information includes:
classifying orders in the historical order data according to the merchant classification information;
and determining the merchant classification to be recommended according to the classification result.
B11. According to the merchant recommendation method in B9, determining the merchant category to be recommended according to the historical order data and the merchant category information includes:
respectively determining the commercial tenants to which the orders in the historical order data belong;
classifying the determined commercial tenants according to the commercial tenant classification information;
and determining the merchant classification to be recommended according to the classification result.
An embodiment of the present application further provides a device for classifying merchants, including:
the acquisition module is used for acquiring historical order data;
the clustering module is used for clustering the order data according to the user information of the order data;
the determining module is used for determining classification characteristics according to the relevancy of each merchant in the clustered order data;
and the classification module is used for classifying the merchants to be classified according to the classification characteristics.
An embodiment of the present application further provides a recommendation apparatus for a merchant, including:
the acquisition module is used for acquiring historical order data of a user;
the classification determining module is used for determining the classification of the commercial tenant to be recommended according to the historical order data and the commercial tenant classification information;
the recommending module is used for recommending the subordinate merchants of the determined merchant classification to the user;
wherein the merchant classification information is from the merchant classification device of 12.
An embodiment of the present application further provides an electronic device, including: a memory storing a computer program and a processor executing the program to perform:
acquiring historical order data, and clustering the order data according to user information of the order data;
determining classification characteristics according to the relevancy of each merchant in the clustered order data;
and classifying the merchants to be classified according to the classification characteristics.
An embodiment of the present application further provides an electronic device, including: a memory storing a computer program and a processor executing the program to perform:
acquiring historical order data of a user;
determining merchant classification to be recommended according to the historical order data and the merchant classification information;
recommending subordinate merchants of the determined merchant classification to the user;
wherein the merchant classification information is from the merchant classification method of any one of the A1-A8.
The embodiment of the present application further provides a non-volatile storage medium, which is used for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute the merchant classification method as described in any one of the methods a1 to A8.
A non-volatile storage medium storing a computer-readable program for causing a computer to perform the merchant recommendation method according to any one of B9 through B11 is also provided in an embodiment of the present application.
Claims (15)
1. A merchant classification method, comprising:
acquiring historical order data, and clustering the order data according to user information of the order data;
determining classification characteristics according to the relevancy of each merchant in the clustered order data;
the merchant with the highest correlation degree is the merchant ordered by the same user, and the merchant with the lowest correlation degree is the merchant ordered by different users;
classifying the commercial tenants to be classified according to the classification characteristics;
the determining of the classification characteristics according to the relevancy of each merchant in the clustered order data specifically comprises:
determining a training sample according to the relevancy of each merchant in the clustered order data;
training by using the training sample to obtain a neural network model, wherein the input of the neural network model is at least two commercial tenants, and the output of the neural network model is the similarity of the at least two commercial tenants;
and determining the classification characteristic according to the middle layer of the neural network model.
2. The merchant classification method according to claim 1, wherein the neural network model is a single-layer neural network model.
3. The merchant classification method according to claim 1, wherein the intermediate layer is preset with a width, and the larger the width is, the larger the number of the determined features of the classification features is.
4. The merchant classification method according to claim 2, wherein the intermediate layer of the single-layer neural network is obtained by:
and minimizing the distance of the merchant with the highest correlation degree, and maximizing the distance of the merchant with the lowest correlation degree to obtain the middle layer.
5. The merchant classification method according to claim 1, wherein the clustering the order data according to the user information of the order data includes:
respectively summarizing the order data of the same type of user;
and classifying the summarized order data.
6. The merchant classification method according to claim 5, wherein the classifying the aggregated order data specifically includes:
and recording the order data belonging to the same class in the classification result as a document file.
7. A merchant recommendation method is characterized by comprising the following steps:
acquiring historical order data of a user;
determining merchant classification to be recommended according to the historical order data and the merchant classification information;
recommending subordinate merchants of the determined merchant classification to the user;
wherein the merchant classification information is from the merchant classification method of any one of claims 1 to 6.
8. The merchant recommendation method according to claim 7, wherein the determining the merchant category to be recommended according to the historical order data and the merchant category information includes:
classifying orders in the historical order data according to the merchant classification information;
and determining the merchant classification to be recommended according to the classification result.
9. The merchant recommendation method according to claim 7, wherein the determining the merchant category to be recommended according to the historical order data and the merchant category information includes:
respectively determining the commercial tenants to which the orders in the historical order data belong;
classifying the determined commercial tenants according to the commercial tenant classification information;
and determining the merchant classification to be recommended according to the classification result.
10. A merchant classifying apparatus, comprising:
the acquisition module is used for acquiring historical order data;
the clustering module is used for clustering the order data according to the user information of the order data;
the determining module is used for determining classification characteristics according to the relevancy of each merchant in the clustered order data;
the classification module is used for classifying the merchants to be classified according to the classification characteristics;
wherein the clustering module comprises:
the sample determining submodule is used for determining a training sample according to the correlation degree of each merchant in the clustered order data;
the training submodule is used for training by utilizing a training sample to obtain a neural network model, the input of the neural network model is at least two commercial tenants, and the output of the neural network model is the similarity of the at least two commercial tenants; and
and the determining submodule is used for determining the classification characteristics according to the middle layer of the neural network model.
11. A merchant recommendation apparatus, comprising:
the acquisition module is used for acquiring historical order data of a user;
the classification determining module is used for determining the classification of the commercial tenant to be recommended according to the historical order data and the commercial tenant classification information;
the recommending module is used for recommending the subordinate merchants of the determined merchant classification to the user;
wherein the merchant classification information is from the merchant classification apparatus of claim 10.
12. An electronic device, comprising: a memory storing a computer program and a processor executing the program to perform:
acquiring historical order data, and clustering the order data according to user information of the order data;
determining classification characteristics according to the relevancy of each merchant in the clustered order data;
classifying the commercial tenants to be classified according to the classification characteristics;
the determining of the classification characteristics according to the relevancy of each merchant in the clustered order data specifically comprises:
determining a training sample according to the relevancy of each merchant in the clustered order data;
training by using the training sample to obtain a neural network model, wherein the input of the neural network model is at least two commercial tenants, and the output of the neural network model is the similarity of the at least two commercial tenants;
and determining the classification characteristic according to the middle layer of the neural network model.
13. An electronic device, comprising: a memory storing a computer program and a processor executing the program to perform:
acquiring historical order data of a user;
determining merchant classification to be recommended according to the historical order data and the merchant classification information;
recommending subordinate merchants of the determined merchant classification to the user;
wherein the merchant classification information is from the merchant classification method of any one of claims 1 to 6.
14. A non-volatile storage medium storing a computer-readable program for causing a computer to execute the method of classifying a merchant according to any one of claims 1 to 6.
15. A non-volatile storage medium storing a computer-readable program for causing a computer to execute the merchant recommendation method according to any one of claims 7 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534645.8A CN109597858B (en) | 2018-12-14 | 2018-12-14 | Merchant classification method and device and merchant recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534645.8A CN109597858B (en) | 2018-12-14 | 2018-12-14 | Merchant classification method and device and merchant recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109597858A CN109597858A (en) | 2019-04-09 |
| CN109597858B true CN109597858B (en) | 2021-09-14 |
Family
ID=65960812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811534645.8A Active CN109597858B (en) | 2018-12-14 | 2018-12-14 | Merchant classification method and device and merchant recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109597858B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210905A (en) * | 2019-05-31 | 2019-09-06 | 拉扎斯网络科技（上海）有限公司 | Characteristic similarity calculation method, device, electronic equipment and computer storage medium |
| CN111242165B (en) * | 2019-12-30 | 2020-10-23 | 北京顺达同行科技有限公司 | Merchant clustering method and device, computer equipment and storage medium |
| CN111475691B (en) * | 2020-03-06 | 2021-11-02 | 拉扎斯网络科技（上海）有限公司 | Method and device for acquiring recommended object data and electronic equipment |
| CN111526037A (en) * | 2020-03-23 | 2020-08-11 | 北京三快在线科技有限公司 | Configuration method and device of network node, electronic equipment and readable storage medium |
| CN111667012B (en) * | 2020-06-10 | 2023-06-06 | 创新奇智(广州)科技有限公司 | Classification result correction method, device, correction equipment and readable storage medium |
| CN114417964B (en) * | 2021-12-10 | 2023-09-12 | 中国卫通集团股份有限公司 | Satellite operator classification method and device and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101996215A (en) * | 2009-08-27 | 2011-03-30 | 阿里巴巴集团控股有限公司 | Information matching method and system applied to e-commerce website |
| CN102930449A (en) * | 2012-11-12 | 2013-02-13 | 侯爵 | Online trade platform and method |
| CN105205689A (en) * | 2015-08-26 | 2015-12-30 | 深圳市万音达科技有限公司 | Method and system for recommending commercial tenant |
| WO2016091173A1 (en) * | 2014-12-09 | 2016-06-16 | 北京嘀嘀无限科技发展有限公司 | User maintenance system and method |
| CN106408326A (en) * | 2016-08-30 | 2017-02-15 | 常州航加网络科技有限公司 | Intelligent information management platform and management method thereof |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN108182621A (en) * | 2017-12-07 | 2018-06-19 | 合肥美的智能科技有限公司 | The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005012665A1 (en) * | 2005-03-18 | 2006-09-21 | Siemens Ag | Method for determining order of data arranged in computer from cluster involves partial correlation of order, they comprises components such as services and products, which occurs partially at several times |
| CN101404078A (en) * | 2008-09-16 | 2009-04-08 | 鲁东大学 | Cooperated electronic market based on market union |
| CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
| CN102760335B (en) * | 2012-07-18 | 2014-11-26 | 朱磊 | Intelligent wireless mobile cash register system and implementation method thereof |
| CN103065258A (en) * | 2012-12-25 | 2013-04-24 | 苏州博康生物医疗科技有限公司 | Method for achieving intelligent service platform |
| CN103489108A (en) * | 2013-08-22 | 2014-01-01 | 浙江工商大学 | Large-scale order form matching method in community commerce cloud |
-
2018
- 2018-12-14 CN CN201811534645.8A patent/CN109597858B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101996215A (en) * | 2009-08-27 | 2011-03-30 | 阿里巴巴集团控股有限公司 | Information matching method and system applied to e-commerce website |
| CN102930449A (en) * | 2012-11-12 | 2013-02-13 | 侯爵 | Online trade platform and method |
| WO2016091173A1 (en) * | 2014-12-09 | 2016-06-16 | 北京嘀嘀无限科技发展有限公司 | User maintenance system and method |
| CN105205689A (en) * | 2015-08-26 | 2015-12-30 | 深圳市万音达科技有限公司 | Method and system for recommending commercial tenant |
| CN106408326A (en) * | 2016-08-30 | 2017-02-15 | 常州航加网络科技有限公司 | Intelligent information management platform and management method thereof |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN108182621A (en) * | 2017-12-07 | 2018-06-19 | 合肥美的智能科技有限公司 | The Method of Commodity Recommendation and device for recommending the commodity, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109597858A (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597858B (en) | Merchant classification method and device and merchant recommendation method and device | |
| CN109408665B (en) | Information recommendation method and device and storage medium | |
| TWI636416B (en) | Method and system for multi-phase ranking for content personalization | |
| WO2020048084A1 (en) | Resource recommendation method and apparatus, computer device, and computer-readable storage medium | |
| CN107862022B (en) | Culture resource recommendation system | |
| CN109242612B (en) | Product recommendation method and device | |
| CN110321422A (en) | Method, method for pushing, device and the equipment of on-line training model | |
| CN109634698B (en) | Menu display method and device, computer equipment and storage medium | |
| CN110196904B (en) | Method and device for acquiring recommendation information and computer readable storage medium | |
| CN106651542A (en) | Goods recommendation method and apparatus | |
| CN107797894B (en) | APP user behavior analysis method and device | |
| CN109614556B (en) | Access path prediction and information push method and device | |
| KR101827345B1 (en) | Personalized recommendation system and its method using multiple algorithms and self-learning function | |
| CN106604051A (en) | Live channel recommending method and device | |
| WO2014148948A1 (en) | Method for selecting valid variants in search and recommendation systems (variants) | |
| CN109272408A (en) | Vehicle loan financial product intelligent recommendation method, apparatus, equipment and medium | |
| CN107590267A (en) | Information-pushing method and device, terminal and readable storage medium storing program for executing based on picture | |
| CN109300041A (en) | Typical karst ecosystem recommended method, electronic device and readable storage medium storing program for executing | |
| CN106843941A (en) | Information processing method, device and computer equipment | |
| CN106919588A (en) | A kind of application program search system and method | |
| CN111105297A (en) | Information pushing method and related device | |
| CN102043811A (en) | Method and system for evaluating medical information | |
| CN106021423B (en) | META Search Engine personalization results recommended method based on group division | |
| CN105389714B (en) | Method for identifying user characteristics from behavior data | |
| CN110134812A (en) | A kind of face searching method and its device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |